Many types of sensors are nonlinear in nature but require an output that is linear. If linear approximation is accepted, for a given accuracy level, noise and measurement errors are always present. Therefore, curve-fitting techniques are frequently required to average these effects. The problem of estimating the sensor's input-output characteristics is being increasingly tackled using software techniques. This paper describes an experimental method for the estimation of nonlinearity, testing and calibrating of the different thermocouple types using artificial neural network (ANN) based algorithms integrated in a virtual instrument (VI). An ANN and a data acquisition board with designed signal conditioning unit are used for data optimization and to collect experimental data, respectively. In both training and testing phases of the ANN, the Wavetek 9100 calibration unit is used to obtain experimental data. After the successful training completion of the ANN, it is then used as a neural linearizer to calculate the temperature from the thermocouple's output voltage. (C) 2006 Elsevier Ltd. All rights reserved.